Skip to content
InfoResearchPreprintLLM-specific

Intent Contracts: Taking Tools Away from Agents

Published
Record updated
View JSON

Summary

Intent contracts are an authorization interface for tool-using LLM agents, in which the planning model holds no tools and submits a logged contract per step. A trusted model checks the contract against the user's words and writes the tool call. Contracts completed the user's task in 27/30 runs with planner-added work, versus 16/30 for an intent-visible reviewer, but they do not reduce unauthorized actions, and wrong-target errors occurred in 40-49% of runs.